EP0722577A1 - Multi-layer opto-electronic neural network - Google Patents
Multi-layer opto-electronic neural networkInfo
- Publication number
- EP0722577A1 EP0722577A1 EP94921271A EP94921271A EP0722577A1 EP 0722577 A1 EP0722577 A1 EP 0722577A1 EP 94921271 A EP94921271 A EP 94921271A EP 94921271 A EP94921271 A EP 94921271A EP 0722577 A1 EP0722577 A1 EP 0722577A1
- Authority
- EP
- European Patent Office
- Prior art keywords
- plane
- medium
- mloenn
- neural network
- pattern
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000013528 artificial neural network Methods 0.000 title claims description 37
- 230000005693 optoelectronics Effects 0.000 title claims description 19
- 239000013598 vector Substances 0.000 claims abstract description 68
- 238000012545 processing Methods 0.000 claims abstract description 20
- 238000000034 method Methods 0.000 claims abstract description 15
- 238000001228 spectrum Methods 0.000 claims abstract description 8
- 230000004044 response Effects 0.000 claims abstract description 7
- 230000006870 function Effects 0.000 claims description 16
- 230000003287 optical effect Effects 0.000 claims description 12
- 238000009826 distribution Methods 0.000 claims description 9
- 238000001914 filtration Methods 0.000 claims description 7
- 230000005684 electric field Effects 0.000 claims description 6
- 238000012546 transfer Methods 0.000 claims description 5
- 238000005311 autocorrelation function Methods 0.000 claims description 4
- 238000003909 pattern recognition Methods 0.000 claims description 4
- 230000001427 coherent effect Effects 0.000 claims description 3
- GQYHUHYESMUTHG-UHFFFAOYSA-N lithium niobate Chemical compound [Li+].[O-][Nb](=O)=O GQYHUHYESMUTHG-UHFFFAOYSA-N 0.000 claims description 3
- 239000004988 Nematic liquid crystal Substances 0.000 claims description 2
- WOIHABYNKOEWFG-UHFFFAOYSA-N [Sr].[Ba] Chemical compound [Sr].[Ba] WOIHABYNKOEWFG-UHFFFAOYSA-N 0.000 claims description 2
- 238000001514 detection method Methods 0.000 claims description 2
- 239000005262 ferroelectric liquid crystals (FLCs) Substances 0.000 claims description 2
- 239000000463 material Substances 0.000 claims description 2
- 230000005284 excitation Effects 0.000 claims 1
- 230000001537 neural effect Effects 0.000 abstract description 5
- 239000010410 layer Substances 0.000 description 41
- 210000002569 neuron Anatomy 0.000 description 8
- 230000008569 process Effects 0.000 description 4
- 230000000875 corresponding effect Effects 0.000 description 3
- 239000004973 liquid crystal related substance Substances 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 3
- 239000000758 substrate Substances 0.000 description 3
- XUIMIQQOPSSXEZ-UHFFFAOYSA-N Silicon Chemical compound [Si] XUIMIQQOPSSXEZ-UHFFFAOYSA-N 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 238000001093 holography Methods 0.000 description 1
- 239000012528 membrane Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 229910052710 silicon Inorganic materials 0.000 description 1
- 239000010703 silicon Substances 0.000 description 1
- 239000002356 single layer Substances 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 238000002834 transmittance Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G03—PHOTOGRAPHY; CINEMATOGRAPHY; ANALOGOUS TECHNIQUES USING WAVES OTHER THAN OPTICAL WAVES; ELECTROGRAPHY; HOLOGRAPHY
- G03H—HOLOGRAPHIC PROCESSES OR APPARATUS
- G03H1/00—Holographic processes or apparatus using light, infrared or ultraviolet waves for obtaining holograms or for obtaining an image from them; Details peculiar thereto
- G03H1/02—Details of features involved during the holographic process; Replication of holograms without interference recording
- G03H1/024—Hologram nature or properties
- G03H1/0248—Volume holograms
-
- G—PHYSICS
- G03—PHOTOGRAPHY; CINEMATOGRAPHY; ANALOGOUS TECHNIQUES USING WAVES OTHER THAN OPTICAL WAVES; ELECTROGRAPHY; HOLOGRAPHY
- G03H—HOLOGRAPHIC PROCESSES OR APPARATUS
- G03H1/00—Holographic processes or apparatus using light, infrared or ultraviolet waves for obtaining holograms or for obtaining an image from them; Details peculiar thereto
- G03H1/04—Processes or apparatus for producing holograms
- G03H1/16—Processes or apparatus for producing holograms using Fourier transform
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06E—OPTICAL COMPUTING DEVICES; COMPUTING DEVICES USING OTHER RADIATIONS WITH SIMILAR PROPERTIES
- G06E3/00—Devices not provided for in group G06E1/00, e.g. for processing analogue or hybrid data
- G06E3/001—Analogue devices in which mathematical operations are carried out with the aid of optical or electro-optical elements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/06—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
- G06N3/067—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons using optical means
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/88—Image or video recognition using optical means, e.g. reference filters, holographic masks, frequency domain filters or spatial domain filters
- G06V10/89—Image or video recognition using optical means, e.g. reference filters, holographic masks, frequency domain filters or spatial domain filters using frequency domain filters, e.g. Fourier masks implemented on spatial light modulators
- G06V10/893—Image or video recognition using optical means, e.g. reference filters, holographic masks, frequency domain filters or spatial domain filters using frequency domain filters, e.g. Fourier masks implemented on spatial light modulators characterised by the kind of filter
- G06V10/895—Image or video recognition using optical means, e.g. reference filters, holographic masks, frequency domain filters or spatial domain filters using frequency domain filters, e.g. Fourier masks implemented on spatial light modulators characterised by the kind of filter the filter being related to phase processing, e.g. phase-only filters
-
- G—PHYSICS
- G03—PHOTOGRAPHY; CINEMATOGRAPHY; ANALOGOUS TECHNIQUES USING WAVES OTHER THAN OPTICAL WAVES; ELECTROGRAPHY; HOLOGRAPHY
- G03H—HOLOGRAPHIC PROCESSES OR APPARATUS
- G03H1/00—Holographic processes or apparatus using light, infrared or ultraviolet waves for obtaining holograms or for obtaining an image from them; Details peculiar thereto
- G03H1/0005—Adaptation of holography to specific applications
-
- G—PHYSICS
- G03—PHOTOGRAPHY; CINEMATOGRAPHY; ANALOGOUS TECHNIQUES USING WAVES OTHER THAN OPTICAL WAVES; ELECTROGRAPHY; HOLOGRAPHY
- G03H—HOLOGRAPHIC PROCESSES OR APPARATUS
- G03H1/00—Holographic processes or apparatus using light, infrared or ultraviolet waves for obtaining holograms or for obtaining an image from them; Details peculiar thereto
- G03H1/26—Processes or apparatus specially adapted to produce multiple sub- holograms or to obtain images from them, e.g. multicolour technique
- G03H1/2645—Multiplexing processes, e.g. aperture, shift, or wavefront multiplexing
- G03H1/265—Angle multiplexing; Multichannel holograms
-
- G—PHYSICS
- G03—PHOTOGRAPHY; CINEMATOGRAPHY; ANALOGOUS TECHNIQUES USING WAVES OTHER THAN OPTICAL WAVES; ELECTROGRAPHY; HOLOGRAPHY
- G03H—HOLOGRAPHIC PROCESSES OR APPARATUS
- G03H1/00—Holographic processes or apparatus using light, infrared or ultraviolet waves for obtaining holograms or for obtaining an image from them; Details peculiar thereto
- G03H1/0005—Adaptation of holography to specific applications
- G03H2001/0066—Adaptation of holography to specific applications for wavefront matching wherein the hologram is arranged to convert a predetermined wavefront into a comprehensive wave, e.g. associative memory
-
- G—PHYSICS
- G03—PHOTOGRAPHY; CINEMATOGRAPHY; ANALOGOUS TECHNIQUES USING WAVES OTHER THAN OPTICAL WAVES; ELECTROGRAPHY; HOLOGRAPHY
- G03H—HOLOGRAPHIC PROCESSES OR APPARATUS
- G03H2260/00—Recording materials or recording processes
- G03H2260/50—Reactivity or recording processes
- G03H2260/54—Photorefractive reactivity wherein light induces photo-generation, redistribution and trapping of charges then a modification of refractive index, e.g. photorefractive polymer
Definitions
- This invention relates to a three-dimensional volume holographic medium in which a multi-layer, opto-electronic neural network is used to classify patterns, and to a method of operating same.
- Multi-layer neural networks may be used to classify patterns. These networks typically consist of layers of nonlinear processing elements or "neurons" arranged in a highly interconnected hierarchy. Each neuron within the top layer of the network hierarchy accepts as input a weighted sum over all of the resolution elements of the pattern to be classified. Each of these sums is then nonlinearly processed by each top-layer neuron and outputted to the second layer of the network, in which each neuron accepts as input a weighted sum over all neural outputs of the first layer. This process continues until the output, or classification, layer of the network is reached. The outputs of this layer are then interpreted as the desired classification results.
- the pattern vector ⁇ a) is the input to layer "i"; the matrix R r represents the neuron input weights; N is the number of network layers; and f[*] is a nonlinear vector function which operates identically on each element of £ ) .
- g [ - ] operates on each element "k" of £ (i) as indicated in Figure l.
- the particular nonlinear transfer function illustrated in Figure 1 has what is commonly referred to as a sigmoidal shape, with adjustable threshold (“a”) and saturation ("b”) points.
- Figure 2 shows an illustrative example of a three- layer neural network consisting of a three-resolution- element input pattern with two output classes. Each layer consists of a fully interconnected set of weights connecting the input to the summers. The output from the summers is fed through a nonlinearity, which completes the processing for that layer. The output from one layer serves as input to the next layer.
- Pattern classification problems in which input patterns are two-dimensional images typically require two- layer neural networks which may contain as many as 10 2 classification-layer neurons and 10 3 input-layer neurons.
- R m becomes a 10 4 x 10 3 -element matrix
- R ⁇ ) a 10 3 x 10 2 -element matrix.
- Existing, all-digital electronic computers capable of such throughput occupy many cubic feet of volume and consume thousands of watts of power.
- Optical devices in which the matrices R f may be stored in the form of two-dimensional Fourier-space holograms include those described by: D. Gabor in "Character Recognition by Holography” in Nature. 208. p. 422 (1965) ; J.T. LaMacchia and D.L. White in “Coded Multiple Exposure Holograms", Applied Optics. 7. p. 91 (1968); J.R. Leger and S.H. Lee in "Hybrid Optical Processor for Pattern Recognition and Classification Using a Generalized Set of Pattern Functions", Applied Optics. 21. p. 274 (1982); and D.A. Gregory and H.K.
- multi-layer, neural network weight matrices are stored in the form of three-dimensional, Fourier-space holograms, with each hologram corresponding to a single row of an individual R r . These rows are referred to hereafter as weight vectors. All weight vectors of a given R c,) are accessed simultaneously (in parallel) by illuminating the volume holograms with the Fourier transform of the pattern or input vector, ffd ) , which is to be weighted (or multiplied) by the R Cl) in question.
- Elements of the product vectors f ⁇ 1] are determined by measuring the properties of the light radiated by the volume holograms: the angle of each of the light rays radiated indexes the element (i.e., indicates which weight vector is being multiplied or dotted onto the input vector ⁇ (i) ) while the amplitude of each of the light rays radiated is proportional to the square of the magnitude of the indexed inner product.
- Nonlinear processing of the individual elements of the product vector, (l) is accomplished by focusing each radiated light ray onto a detector array element and further processing the detector array output using, for example, an electronic look-up table or a saturable electronic amplifier with adjustable thresholding and saturation points.
- the present invention enables more weight- vector information (the product of weight-vector count and weight-vector size) to be accessed in parallel than do the aforementioned devices, wherein weight vectors are stored in the form of two-dimensional Fourier-space holograms.
- the ratio of storage capabilities (storage capacity of a three-dimensional-hologram device divided by the storage capacity of a two-dimensional hologram device) is equal to the maximum (linear) space-bandwidth product, or number of linearly ordered resolution elements, that can be achieved in an optical system. The latter number is typically on the order of 3,000. More specifically, the invention provides a pattern classification apparatus and a method for operating same.
- the apparatus includes a volume-holographic medium having a plurality of Fourier-space volume holograms representing stored weight vectors.
- the apparatus further includes a spatial light modulator and a phase encoder.
- the phase encoder has an output optically coupled to the volume- holographic medium by a first Fourier transform lens.
- the spatial light modulator spatially modulates a spatially uniform laser beam in accordance with an unknown pattern which has been loaded into the spatial light modulator.
- the two-dimensional phase encoder causes the spatially modulated laser beam to be spatially distributed prior to application to the volume-holographic medium.
- the apparatus also includes a detector having an input optically coupled by a second Fourier transform lens means to an angular spectrum of plane waves generated by the volume-holographic medium in response to the output of the spatial modulator, phase encoder, and first Fourier lens.
- the detector detects focused plane waves that correspond to vector inner products generated within the volume- holographic medium in response to the unknown pattern vector.
- the apparatus further includes a nonlinear electronic device for serially processing the detected inner products, means for temporarily storing the nonlinearly processed inner products, and means for feeding the nonlinearly processed inner products back into the spatial light modulator.
- Fig. 1 depicts nonlinear processing of element "k" of the neural input vector, ⁇ ) 1 k , to produce a corres- ponding element of the neural output vector, [ ⁇ (i * 1) ] k , "a" and “b” being thresholding and saturation points, respect ⁇ ively, of the resulting sigmoidal neural transfer function;
- Fig. 2 schematically depicts an example of a three- layer neural network
- Fig. 3 is a perspective drawing of a multi-layer opto ⁇ electronic neural network (MLOENN) of the invention
- Fig. 5 depicts the spatial light modulator geometry used to store the weight vectors of an N-layer neural network;
- Fig. 6 illustrates the spatial light modulator used to sequentially process patterns ⁇ (1> (the input pattern to the neural network) through ⁇ (the input to the last layer of the neural network) ;
- Fig. 8 is a plan view of the MLOENN illustrating the generation, detection, and nonlinear processing of a single vector inner product, fj. (i) ;
- the Multi-Layer Opto-Electronic Neural Network classifies patterns by repeatedly executing the algorithm described by Equation (1) .
- This algorithm consists of: (1) calculating the matrix-vector product R ⁇ i) ⁇ (i) to yield f (i) , and (2) nonlinearly processing £ (l) to yield ⁇ (i * 1] , which then becomes the input to the next network layer.
- the network is virtual in the sense that only one layer actually "exists" at a time: intermediate results (i.e., ⁇ ) for i > 1) are temporarily stored in a buffer memory prior to being fed back into the MLOENN for further processing.
- the MLOENN calculates R (i) ⁇ (i) by computing, in parallel, the inner products between the rows of R r,) (hereafter referred to as weight vectors) and ⁇ (1) Mathematically, the MLOENN calculates:
- v'*' ' is the transpose of the k A row of R r,)
- f ⁇ i] is the k ⁇ element of f (l)
- K is the number of rows of flt ⁇ # fl- V - i . i s a lexicographic representation of the input pattern ⁇ r (or intermediate neural network result being processed) , wherein each resolution element or pixel of ⁇ r corresponds to a specific element of ⁇ (i) .
- the MLOENN nonlinearly processes the f 1 ⁇ by serially passing the latter through any electronic device with an appropriate, nonlinear transfer function (as illustrated by the example shown in Figure 1) .
- the MLOENN includes a two-dimensional spatial light modulator (SLM) 1, a two-dimensional phase encoder 2, a first Fourier transform lens 3, a medium 4 in which volume holograms are stored, a second Fourier transform lens 5, a linear detector array 6, a nonlinear processing device 12, and a buffer memory 13.
- SLM spatial light modulator
- SLM 1 includes means for electronically inputting a weight vector or pattern.
- SLM 1 may be comprised of a liquid crystal (LC) projection display device having a plurality of pixels that are modified in response to input from, for example, a digital computer.
- LC liquid crystal
- the use of a LC projection display device enables a new input pattern or weight vector to be stored within medium 4 every, for example, 1/30th of a second.
- Any one of a number of spatial light modulator types may be employed. These include ferroelectric liquid crystal, twisted nematic liquid crystal, silicon membrane
- SLM 1 may be simply a transparent substrate having a pattern formed thereon.
- Two-dimensional phase encoder 2 causes the optical signal that passes through SLM 1 to be spatially distributed prior to application to medium 4. This function may be accomplished by constructing phase encoder 2 from a transparent substrate, such as glass, and providing an etched random pattern on a surface of the substrate. The linear dimension of the smallest feature of the random pattern defines the coherence length of phase encoder 2. The significance of the coherence length of the phase encoder is discussed below.
- Fourier transform lenses 3 and 5 are typically spherical lenses.
- a presently preferred volume hologram medium 4 is comprised of iron-doped lithium niobate (LiNb0 3 :Fe) . Representative dimensions of the active volume of medium 4 are one centimeter on a side. Holograms may be "permanently" fixed by heating the LiNb0 3 :Fe to approximately 160° C for approximately twenty-five seconds (see, for example, D.L. Staebler, W.J. Burk, W. Phillips, and J.J. Amodei in "Multiple storage and exposure of fixed holograms in Fe-doped LiNb0 3 ", Applied Physics Letters, Vol. 26, p. 182 (1975)).
- Holograms fixed in such a manner are estimated to have a half-life of approximately 100,000 years at room temperature.
- Other suitable volume hologram media include, by example, strontium barium niobate (SrBaNb0 3 ) , photorefractive photopolymers, and photochemical photopolymers.
- Linear detector array 6 may be, for example, a charge- coupled device (CCD) , a self-scanned diode array, a Schottky diode array, a pyroelectric device array, or other device capable of converting optical photons into an electronic voltage or current.
- Linear detector array 6 has a resolution, or number of photoresponsive elements, equal to the number of templates stored within medium 4.
- Nonlinear processor 12 may be any electronic device with an appropriately shaped transfer function. Examples include digital electronic look-up tables and saturable electronic amplifiers. Buffer memory 13 may be any digital electronic memory.
- Fig. 4 illustrates the storage of weight vectors within the medium 4. Weight vectors are stored within medium 4 in the following manner:
- weight vector *-- 0 is loaded into SLM 1 using a predetermined and fixed lexicographic ordering scheme;
- SLM 1 spatially modulates a spatially uniform, plane-wave laser beam 7;
- phase encoder 2 multiplies the light pattern transmitted by SLM 1 by a random, two-dimensional phase encoding function; 4. first Fourier transform lens 3 (which is positioned one focal length (Jf,) from phase encoder 2 and one focal length (f,) from the midpoint of medium 4) generates (at approximately the midpoint of medium 4) the Fourier transform of the light pattern transmitted by phase encoder 2;
- reference plane-wave laser beam 8 (which is temporally coherent with plane-wave laser beam 7) illuminates medium 4 at angle k to the z 2 - axis of medium 4 and within the x 2 - z 2 plane;
- weight vector hologram V ⁇ 0 forms within medium 4.
- a predetermined and fixed lexicographic ordering scheme is intended to mean that weight vectors are presented to the system in a consistent manner. For example, if the weight vector is derived from a television camera having a plurality of scanlines, the scanlines are input in the same order for each weight vector. The scanlines need not be input sequentially, so long as they are input consistently.
- the SLM geometry shown in Figure 5 is capable of storing N interconnect matrices, each having a maximum of K rows. Matrices having fewer than K rows may be stored by simply blocking (i.e., electronically setting to zero) the appropriate portions of the SLM.
- Figure 6 illustrates the SLM geometry used to sequentially process patterns ⁇ (1> through ⁇ m .
- ff ⁇ -> (the input pattern to be classified) is first loaded into the SLM (all other regions of the SLM are electronically set to zero, i.e. to block plane-wave laser beam 7) as shown in Fig. 6a.
- ⁇ (2) is then fetched from temporary memory 13 and loaded into the SLM as shown in Fig. 6b.
- the same procedure is followed until ⁇ m is loaded as shown in Fig. 6c, at which time memory 13 contains the desired pattern classification results.
- the geometry shown in Fig. 6 corresponds exactly to the geometry shown in Fig. 5, i.e., ⁇ f( . n) occupies the exact same physical portion of the SLM as ⁇ (D) .
- Plane-wave laser beam 7 may originate from, for example, an argon-ion laser having a wavelength of 4875 A.
- the reference plane-wave laser beam 8 originates from the same source. It is also within the scope of the invention to maintain medium 4, if comprised of iron-doped lithium niobate, at a temperature of approximately 130° C while the weight vectors are being inputted. This results in a simultaneous storing and fixing of the weight vectors. For this case, some shrinkage of medium 4 occurs when same is cooled and plane-wave laser beam 7 is required to have a slightly shorter wavelength so as to compensate for the shrinkage of the material when applying an unknown pattern to the MLOENN.
- phase encoder 2 beneficially diffuses or spreads out the light energy so that the energy is uniformly distributed throughout the volume of medium 4. If phase encoder 2 were not used, the light energy from successive weight vectors would be focused to within a small region within the volume of medium 4. This would result in a reduction in storage capacity and an increase in optical crosstalk.
- reference laser beam 8 is scanned through a plane of medium 4.
- reference plane-wave laser beam 8 may be scanned through plus or minus five degrees, referenced to the center of the medium 4, in 0.01 degree increments. That is, after a weight vector is stored, reference plane- wave laser beam 8 is shifted by 0.01 degrees before the storage of a next weight vector.
- Fig. 7 illustrates the generation of vector inner products.
- the inner products, f* 1 ' (elements of ) ) are generated in the following manner: 1. pattern vector ⁇ (i) is loaded into SLM 1 using the same pre-determined and fixed lexicographic ordering scheme used to load the *'- 1 ' ;
- phase encoder 2 multiplies the light pattern transmitted by SLM 1 by a random, two-dimensional phase encoding function
- first Fourier transform lens 3 generates (at approximately the midpoint of medium 4) the Fourier transform of the light pattern transmitted by phase encoder 2;
- second Fourier transform lens 5 located one focal length (f 2 ) from the midpoint of medium 4, focuses each plane wave (of the angular spectrum of plane waves) generated within volume hologram medium 4 onto linear detector array 6 located one focal length (f 2 ) from second Fourier transform lens 5;
- nonlinear processor 12 is temporarily stored within buffer memory 13; and 10. the contents of buffer memory 13 are either read out and interpreted as classification results or fed back into SLM 1 for further, multi-layer network processing.
- ⁇ is the two-dimensional electric field distribution which corresponds to ⁇ ;
- ⁇ is the two-dimensional phase encoding function characteristic of phase encoder 2 (see, for example, C. N. Kurtz in "The transmittance characteristics of surface diffusers and the design of nearly band-limited binary diffusers", Journal of the Optical Society of America, Vol. 62, p. 982 (1972); and
- F ⁇ • ⁇ denotes Fourier transform; and for a refractive index distribution within volume hologram medium 4 proportional to
- a k is the amplitude of reference plane-wave laser beam 8 associated with weight vector v*, ( • ) * denotes complex conjugate, and j> k is the two-dimensional field distribution given by
- In-plane spatial filtering occurs as a natural result of Bragg selectivity within the volume hologram medium 4 (see, for example, T. Jannson, H.M. Stoll, and C. Karaguleff in "The interconnectability of neuro-optic processors", Proceedings of the International Society for Optical Engineering, Vol. 698, p. 157 (1986)).
- phase encoder 2 Spatial filtering perpendicular to the plane of the processors occurs as a result of phase encoder 2's autocorrelation function of being much narrower (- ten times) than either the autocorrelation function of a or any of the autocorrelation functions of the v*.
- phase encoder 2 is assumed to be significantly smaller than (e.g., less than 10% as large as) the smallest linear dimension of a resolution element of either ⁇ or any of the v*.
- the double integral in Equation (7) is taken over the correlation plane.
- E ⁇ 3> may, following lexicographic ordering, be re ⁇ written as:
- ⁇ ( ' ) is the dirac delta function; the x-dimension lies both within the correlation plane and within the plane of the holographic inner product processor; and [ • , • ] denotes vector inner product.
- Field E (3) represents the inner product of ⁇ with each of the weight vectors v* , which is the desired result.
- a two-dimensional detector array 11 may be employed for a system that scans, during weight vector storage, reference laser beam 8 in two dimensions.
- the two-dimensional detector array 11 may then be a staring type array.
- fractal storage geometry considerations are employed to select reference laser beam 8 angles so as to avoid crosstalk within medium 4.
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- Optics & Photonics (AREA)
- Neurology (AREA)
- Artificial Intelligence (AREA)
- Nonlinear Science (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Holo Graphy (AREA)
Abstract
Description
Claims
Applications Claiming Priority (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US08/099,882 US5497253A (en) | 1988-07-18 | 1993-07-30 | Multi-layer opto-electronic neural network |
US99882 | 1993-07-30 | ||
PCT/US1994/006508 WO1995004309A1 (en) | 1993-07-30 | 1994-06-07 | Multi-layer opto-electronic neural network |
Publications (4)
Publication Number | Publication Date |
---|---|
EP0722577A1 true EP0722577A1 (en) | 1996-07-24 |
EP0722577A4 EP0722577A4 (en) | 2001-01-31 |
EP0722577B1 EP0722577B1 (en) | 2003-12-10 |
EP0722577B9 EP0722577B9 (en) | 2004-06-09 |
Family
ID=22277074
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
EP94921271A Expired - Lifetime EP0722577B9 (en) | 1993-07-30 | 1994-06-07 | Multi-layer opto-electronic neural network |
Country Status (5)
Country | Link |
---|---|
US (1) | US5497253A (en) |
EP (1) | EP0722577B9 (en) |
JP (1) | JP3638951B2 (en) |
DE (1) | DE69433404T2 (en) |
WO (1) | WO1995004309A1 (en) |
Families Citing this family (22)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
FR2734676B1 (en) * | 1995-05-23 | 1997-08-08 | Labeyrie Antoine | LASER EMISSION OR RECEPTION METHOD AND DEVICES FOR OPTICAL TRANSMISSION OF INFORMATION |
US6601049B1 (en) * | 1996-05-02 | 2003-07-29 | David L. Cooper | Self-adjusting multi-layer neural network architectures and methods therefor |
US6490571B1 (en) * | 1996-05-02 | 2002-12-03 | David L. Cooper | Method and apparatus for neural networking using semantic attractor architecture |
US6558979B2 (en) | 1996-05-21 | 2003-05-06 | Micron Technology, Inc. | Use of palladium in IC manufacturing with conductive polymer bump |
US5664065A (en) * | 1996-06-17 | 1997-09-02 | The United States Of America As Represented By The Secretary Of The Army | Pulse-coupled automatic object recognition system dedicatory clause |
DE19739909A1 (en) * | 1997-09-11 | 1999-03-18 | Philips Patentverwaltung | Method and arrangement for determining distance values |
FR2770912A1 (en) * | 1997-11-07 | 1999-05-14 | Bertin & Cie | Device and method for storing holographic information. |
US6529614B1 (en) * | 1998-08-05 | 2003-03-04 | California Institute Of Technology | Advanced miniature processing handware for ATR applications |
US7515753B2 (en) | 1999-05-19 | 2009-04-07 | Lenslet Labs Ltd. | Phase extraction in optical processing |
WO2000072267A1 (en) * | 1999-05-19 | 2000-11-30 | Lenslet, Ltd. | Image compression |
WO2001004687A1 (en) * | 1999-07-09 | 2001-01-18 | Opts, Inc. | Adaptive compressive network |
US6744909B1 (en) * | 1999-08-19 | 2004-06-01 | Physical Optics Corporation | Authentication system and method |
US6854004B2 (en) | 2001-12-26 | 2005-02-08 | The United States Of America As Represented By The Secretary Of The Navy | Irregular optical interconnections to compensate for non-uniformities in analog optical processors |
US7164429B1 (en) * | 2004-07-07 | 2007-01-16 | Hewlett-Packard Development Company, L.P. | Signal conversion system |
JP7008448B2 (en) * | 2017-09-01 | 2022-01-25 | 日本放送協会 | Hologram recording / playback device |
GB2573171B (en) * | 2018-04-27 | 2021-12-29 | Optalysys Ltd | Optical processing systems |
JP7194596B2 (en) * | 2019-01-08 | 2022-12-22 | 日本放送協会 | Hologram recording and reproducing device |
KR20200092525A (en) | 2019-01-24 | 2020-08-04 | 삼성전자주식회사 | Optical neural network apparatus including passive phase modulator |
JP7212543B2 (en) * | 2019-02-18 | 2023-01-25 | 日本放送協会 | Decoding device, hologram reproducing device, and decoding method |
US20200327403A1 (en) * | 2019-04-15 | 2020-10-15 | The Hong Kong University Of Science And Technology | All optical neural network |
CN110647023B (en) * | 2019-09-16 | 2020-04-28 | 四川大学 | Rapid hologram generation and high-quality reconstruction method based on partial angle spectroscopy |
JPWO2021205547A1 (en) * | 2020-04-07 | 2021-10-14 |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO1989012870A1 (en) * | 1988-06-24 | 1989-12-28 | Thomson-Csf | Device for processing an adaptive, nonlinear signal |
Family Cites Families (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPS573041B2 (en) * | 1974-05-01 | 1982-01-20 | ||
US4949389A (en) * | 1987-10-09 | 1990-08-14 | The United States Of America As Represented By The United States Department Of Energy | Optical ranked-order filtering using threshold decomposition |
US5317651A (en) * | 1988-06-24 | 1994-05-31 | Thomson-Csf | Non-linear and adaptive signal-processing device |
US5235439A (en) * | 1988-07-18 | 1993-08-10 | Northrop Corporation | Volume-holographic inner product processor |
US5132813A (en) * | 1988-08-18 | 1992-07-21 | Teledyne Industries, Inc. | Neural processor with holographic optical paths and nonlinear operating means |
JPH02143391A (en) * | 1988-11-25 | 1990-06-01 | Ricoh Co Ltd | Parallel optical information processor |
US5235440A (en) * | 1989-11-06 | 1993-08-10 | Teledyne Industries, Inc. | Optical interconnector and highly interconnected, learning neural network incorporating optical interconnector therein |
FR2658336A1 (en) * | 1990-02-09 | 1991-08-16 | Philips Electronique Lab | METHOD OF LEARNING A NETWORK OF NEURONS IN LAYERS FOR MULTICLASS CLASSIFICATION AND NETWORK OF NEURONS IN LAYERS. |
US5323472A (en) * | 1990-03-27 | 1994-06-21 | The Boeing Company | Optical image analyzer using optical correlation and opto-electronic feedback |
US5129041A (en) * | 1990-06-08 | 1992-07-07 | Grumman Aerospace Corporation | Optical neural network processing element with multiple holographic element interconnects |
US5121228A (en) * | 1990-09-27 | 1992-06-09 | Bell Communications Research | Holographic learning machine |
US5293456A (en) * | 1991-06-28 | 1994-03-08 | E. I. Du Pont De Nemours And Company | Object recognition system employing a sparse comparison neural network |
-
1993
- 1993-07-30 US US08/099,882 patent/US5497253A/en not_active Expired - Lifetime
-
1994
- 1994-06-07 WO PCT/US1994/006508 patent/WO1995004309A1/en active IP Right Grant
- 1994-06-07 JP JP50580395A patent/JP3638951B2/en not_active Expired - Fee Related
- 1994-06-07 EP EP94921271A patent/EP0722577B9/en not_active Expired - Lifetime
- 1994-06-07 DE DE69433404T patent/DE69433404T2/en not_active Expired - Lifetime
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO1989012870A1 (en) * | 1988-06-24 | 1989-12-28 | Thomson-Csf | Device for processing an adaptive, nonlinear signal |
Non-Patent Citations (1)
Title |
---|
See also references of WO9504309A1 * |
Also Published As
Publication number | Publication date |
---|---|
WO1995004309A1 (en) | 1995-02-09 |
DE69433404D1 (en) | 2004-01-22 |
EP0722577A4 (en) | 2001-01-31 |
JPH09500995A (en) | 1997-01-28 |
EP0722577B1 (en) | 2003-12-10 |
JP3638951B2 (en) | 2005-04-13 |
DE69433404T2 (en) | 2004-09-16 |
US5497253A (en) | 1996-03-05 |
EP0722577B9 (en) | 2004-06-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US5497253A (en) | Multi-layer opto-electronic neural network | |
Wagner et al. | Multilayer optical learning networks | |
Caulfield et al. | Optical neural networks | |
Leger et al. | Hybrid optical processor for pattern recognition and classification using a generalized set of pattern functions | |
Ford et al. | Array interconnection by phase-coded optical correlation | |
US5235439A (en) | Volume-holographic inner product processor | |
Owechko | Optoelectronic resonator neural networks | |
White et al. | Digital and analogue holographic associative memories | |
Marrakchi et al. | Dynamic holographic interconnects with analog weights in photorefractive crystals | |
Owechko | Cascaded-grating holography for artificial neural networks | |
US5412755A (en) | Optical implementation of inner product neural associative memory | |
Owechko et al. | Holographic neurocomputer utilizing laser diode light source | |
Liu et al. | Optical implementation of terminal-attractor-based associative memory | |
Yoshida et al. | Optical computing techniques for image/video compression | |
Owechko et al. | Optoelectronic neural networks based on holographically interconnected image processors | |
Shamir et al. | Improved architectures for massive holographic interconnection network | |
Sasaki et al. | Dynamic digital photorefractive memory for optoelectronic neural network learning modules | |
Wen et al. | Modified two-dimensional Hamming neural network and its optical implementation using Dammann gratings | |
Robinson et al. | Custom electro-optic devices for optically implemented neuromorphic computing systems | |
Takaki | Electro-optical implementation of learning architecture to control point spread function of liquid crystal active lens | |
Jutamulia et al. | Hopfield neural network using electron-trapping materials | |
Cheng | Variable-frequency cross-grating interferometer | |
Kaikhah et al. | Computer generated holograms for optical neural networks | |
Garvin et al. | Real-time signal classification with an acousto-optic triple-product processor cascaded into a volume holographic classifier | |
Paek et al. | VanderLugt correlator and neural networks |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PUAI | Public reference made under article 153(3) epc to a published international application that has entered the european phase |
Free format text: ORIGINAL CODE: 0009012 |
|
17P | Request for examination filed |
Effective date: 19960227 |
|
AK | Designated contracting states |
Kind code of ref document: A1 Designated state(s): DE FR GB IT |
|
A4 | Supplementary search report drawn up and despatched |
Effective date: 20001215 |
|
AK | Designated contracting states |
Kind code of ref document: A4 Designated state(s): DE FR GB IT |
|
RIC1 | Information provided on ipc code assigned before grant |
Free format text: 7G 03H 1/16 A, 7G 06K 9/76 B, 7G 02B 27/46 B, 7G 06N 3/067 B |
|
17Q | First examination report despatched |
Effective date: 20020129 |
|
GRAH | Despatch of communication of intention to grant a patent |
Free format text: ORIGINAL CODE: EPIDOS IGRA |
|
GRAS | Grant fee paid |
Free format text: ORIGINAL CODE: EPIDOSNIGR3 |
|
GRAA | (expected) grant |
Free format text: ORIGINAL CODE: 0009210 |
|
AK | Designated contracting states |
Kind code of ref document: B1 Designated state(s): DE FR GB IT |
|
REG | Reference to a national code |
Ref country code: GB Ref legal event code: FG4D |
|
REF | Corresponds to: |
Ref document number: 69433404 Country of ref document: DE Date of ref document: 20040122 Kind code of ref document: P |
|
ET | Fr: translation filed | ||
PLBE | No opposition filed within time limit |
Free format text: ORIGINAL CODE: 0009261 |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: NO OPPOSITION FILED WITHIN TIME LIMIT |
|
26N | No opposition filed |
Effective date: 20040913 |
|
PGFP | Annual fee paid to national office [announced via postgrant information from national office to epo] |
Ref country code: FR Payment date: 20100706 Year of fee payment: 17 |
|
PGFP | Annual fee paid to national office [announced via postgrant information from national office to epo] |
Ref country code: IT Payment date: 20100621 Year of fee payment: 17 |
|
PGFP | Annual fee paid to national office [announced via postgrant information from national office to epo] |
Ref country code: GB Payment date: 20100401 Year of fee payment: 17 Ref country code: DE Payment date: 20100625 Year of fee payment: 17 |
|
REG | Reference to a national code |
Ref country code: GB Ref legal event code: 732E Free format text: REGISTERED BETWEEN 20110428 AND 20110504 |
|
GBPC | Gb: european patent ceased through non-payment of renewal fee |
Effective date: 20110607 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: IT Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20110607 |
|
REG | Reference to a national code |
Ref country code: FR Ref legal event code: ST Effective date: 20120229 |
|
REG | Reference to a national code |
Ref country code: DE Ref legal event code: R119 Ref document number: 69433404 Country of ref document: DE Effective date: 20120103 |
|
REG | Reference to a national code |
Ref country code: FR Ref legal event code: TP Owner name: NORTHROP GRUMMAN SYSTEMS CORPORATION, US Effective date: 20120314 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: DE Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20120103 Ref country code: FR Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20110630 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: GB Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20110607 |
|
REG | Reference to a national code |
Ref country code: DE Ref legal event code: R082 Ref document number: 69433404 Country of ref document: DE Representative=s name: ANDRAE FLACH HAUG, DE |
|
REG | Reference to a national code |
Ref country code: DE Ref legal event code: R082 Ref document number: 69433404 Country of ref document: DE Representative=s name: ANDRAE WESTENDORP PATENTANWAELTE PARTNERSCHAFT, DE Effective date: 20130205 Ref country code: DE Ref legal event code: R082 Ref document number: 69433404 Country of ref document: DE Representative=s name: ANDRAE FLACH HAUG, DE Effective date: 20130205 Ref country code: DE Ref legal event code: R081 Ref document number: 69433404 Country of ref document: DE Owner name: NORTHROP GRUMMAN SYSTEMS CORPORATION (N.D.GES., US Free format text: FORMER OWNER: NORTHROP GRUMMAN CORP., LOS ANGELES, CALIF., US Effective date: 20130205 Ref country code: DE Ref legal event code: R081 Ref document number: 69433404 Country of ref document: DE Owner name: NORTHROP GRUMMAN SYSTEMS CORPORATION (N.D.GES., US Free format text: FORMER OWNER: NORTHROP GRUMMAN CORP., LOS ANGELES, US Effective date: 20130205 |